CalvinBackup/Awesome-LVLM-Attack
1
0
Fork 0
mirror of https://github.com/liudaizong/Awesome-LVLM-Attack.git synced 2026-02-12 17:42:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

update 7.7.2025

Browse Source
This commit is contained in:
Daizong Liu
2025-07-07 11:44:49 +08:00
committed by GitHub
parent 22ef47a50e
commit 5204ff3e5f
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -359,6 +359,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
* Lei Jiang, Zixun Zhang, Zizhou Wang, Xiaobing Sun, Zhen Li, Liangli Zhen, Xiaohua Xu
* University of Science and Technology of China, The Chinese University of Hong Kong, A*STAR
* [Arxiv2025] https://arxiv.org/abs/2506.16760
* **Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection** | #
* Ziqi Miao, Yi Ding, Lijun Li, Jing Shao
* Shanghai Artificial Intelligence Laboratory, Purdue University
* [Arxiv2025] https://arxiv.org/abs/2507.02844
## Prompt-Injection
* **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |